Semantic Segmentation of Remote Sensing Images with Sparse Annotations

Abstract

Training Convolutional Neural Networks (CNNs) for very high resolution images requires a large quantity of high-quality pixel-level annotations, which is extremely labor- and time-consuming to produce. Moreover, professional photo interpreters might have to be involved for guaranteeing the correctness of annotations. To alleviate such a burden, we propose a framework for semantic segmentation of aerial images based on incomplete annotations, where annotators are asked to label a few pixels with easy-to-draw scribbles. To exploit these sparse scribbled annotations, we propose the FEature and Spatial relaTional regulArization (FESTA) method to complement the supervised task with an unsupervised learning signal that accounts for neighbourhood structures both in spatial and feature terms.

References in corpus (5)

• Deep learning in remote sensing: a review
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
• High-Resolution Semantic Labeling with Convolutional Neural Networks
• Decision fusion with multiple spatial supports by conditional random fields

Cited by in corpus (4)

• A Review on Deep Learning in UAV Remote Sensing
• Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark
• Consistency-Regularized Region-Growing Network for Semantic Segmentation of Urban Scenes with Point-Level Annotations
• Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery